Model catalog profile

NVIDIA: Nemotron Nano 12B 2… | API profile

Start with NVIDIA: Nemotron Nano 12B 2… model ID, modality, and parameter surface, then decide whether to continue to a key check or integration test.

Provider

NVIDIA

11 models in catalog

Context

128,000

global model route

Input

$0.00

USD / 1M tokens

Output

$0.00

USD / 1M tokens

What this page answers

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer

NVIDIA · nvidia/nemotron-nano-12b-v2-vl:free
text+image+video->text · global model route
128,000 context · $0.00 input

Before connecting

Do not stop at the model name. Before integration, verify base URL, protocol, visible models, parameters, and limits together.

supports include_reasoning
supports max_tokens
supports reasoning
supports seed
supports temperature

Next action

After this page, the usual next step is to open the model profile, the provider profile, or run a key check to confirm the real callable range.

Check whether the model fits the use case
Then verify key permission and callable models

Continue

nvidia/nemotron-nano-12b-v2-vl:free